1
0
mirror of https://github.com/golang/go synced 2024-11-18 09:14:43 -07:00

encoding/xml: Do not pass through invalid utf8 bytes

EscapeText now escapes 0xFFFD returned from DecodeRune as 0xFFFD, rather than passing through the original byte.
Fixes #5880.

R=golang-dev, r, bradfitz, adg
CC=golang-dev
https://golang.org/cl/11975043
This commit is contained in:
Alex A Skinner 2013-07-30 14:11:47 +10:00 committed by Andrew Gerrand
parent 51b3611a72
commit 789e1c351e
2 changed files with 13 additions and 1 deletions

View File

@ -1758,7 +1758,7 @@ func EscapeText(w io.Writer, s []byte) error {
case '\r':
esc = esc_cr
default:
if !isInCharacterRange(r) {
if !isInCharacterRange(r) || (r == 0xFFFD && width == 1) {
esc = esc_fffd
break
}

View File

@ -11,6 +11,7 @@ import (
"reflect"
"strings"
"testing"
"unicode/utf8"
)
const testInput = `
@ -714,3 +715,14 @@ func TestEscapeTextInvalidChar(t *testing.T) {
t.Errorf("have %v, want %v", text, expected)
}
}
func TestIssue5880(t *testing.T) {
type T []byte
data, err := Marshal(T{192, 168, 0, 1})
if err != nil {
t.Errorf("Marshal error: %v", err)
}
if !utf8.Valid(data) {
t.Errorf("Marshal generated invalid UTF-8: %x", data)
}
}